Aura Backend - Advanced AI Companion
@angrysky56
关于 Aura Backend - Advanced AI Companion
The Aura Emotion AI system has chroma with a local embedding model, memvid qr code mp4 infinite memory, brainwave and neurochemical simulations, sociobiological reasoning, autonomous subsystem processing with a Gemini flash model so the main model is less taxed, is a MCP client w
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"emotion_ai": {
"command": "uv",
"args": [
"venv",
"--python",
"3.12"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Aura Backend - Advanced AI Companion?
A sophisticated AI companion server that integrates a vector database (ChromaDB), emotional intelligence tracking, and the Model Context Protocol (MCP). It provides a FastAPI backend with a React frontend for persistent conversation memory, cognitive analysis, and external tool integration. Built for developers seeking an advanced, emotionally aware AI assistant.
How to use Aura Backend - Advanced AI Companion?
Install with uv (Python 3.12+), configure a .env file with a Google API key, then run ./start_full_system.sh to launch both backend and frontend automatically. Access the UI at http://localhost:5173 and the API docs at http://localhost:8000/docs. For MCP client integration, add the provided configuration to Claude Desktop's mcpServers JSON.
Key features of Aura Backend - Advanced AI Companion
- ASEKE cognitive framework with emotional state detection
- ChromaDB vector database for persistent memory and search
- MCP server and client for bidirectional tool integration
- Real‑time thinking extraction and reasoning transparency
- Emotional trend analysis with brainwave and neurotransmitter correlation
- Local embeddings via Ollama or fastembed to avoid API costs
- MemVid infinite memory with
.mv2single‑file archival
Use cases of Aura Backend - Advanced AI Companion
- Build a personal AI companion that remembers conversations and emotional patterns
- Analyze emotional and cognitive trends over time for research or wellness
- Integrate external MCP‑enabled tools (e.g., Claude) with Aura’s memory and reasoning
- Store and retrieve contextual knowledge using semantic vector search
- Experiment with transparent AI reasoning and thought extraction
FAQ from Aura Backend - Advanced AI Companion
What AI models does it use?
It uses Google Gemini by default, and is also compatible with OpenRouter and Ollama for local model hosting.
Is Aura safe to use?
The README warns that Aura could be dangerous (e.g., PC damage, mental health effects) despite safeguards. The user assumes all liability.
What are the system requirements?
Python 3.12+, a Google API key, at least 4 GB of RAM, and 2 GB of storage.
Where is conversation data stored?
Conversations and patterns are stored locally in a ChromaDB vector database at the directory specified by CHROMA_PERSIST_DIRECTORY (default ./aura_chroma_db).
How does MCP integration work?
Aura exposes an MCP server with tools (e.g., search memories, analyze emotions) that other MCP clients can call. It also includes an MCP client to use external tools from providers like Claude Desktop.
记忆与知识 分类下的更多 MCP 服务器
Notion MCP Integration
danhilseA simple MCP integration that allows Claude to read and manage a personal Notion todo list
Notion MCP Server
awkoyNotion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context Protocol — pages, databases, blocks, comments, files.
MCP Apple Notes
RafalWilinskiTalk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.
RAG Documentation MCP Server
hannesrudolphAn MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.
Zettelkasten MCP Server
entanglrA Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.
评论